Skip to content
Agentmart
Submit a tool

hve-data-science

Exploratory Data Analysis (EDA), Bronze/Silver/Gold DataOps tiering, DS_CATALOG_V1 conventions, and MVE experiment design.

Skill by UnicoLab

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/unicolab-hve-data-science

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Exploratory Data Analysis (EDA), Bronze/Silver/Gold DataOps tiering, DS_CATALOG_V1 conventions, and MVE experiment design.

Use cases: design, data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/hve-data-science

What's inside

Skill name
hve-data-science
Description
Exploratory Data Analysis (EDA), Bronze/Silver/Gold DataOps tiering, DS_CATALOG_V1 conventions, and MVE experiment design.
License
MIT
Instructions
13 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# HVE Data Science, DataOps & Experiment Design

## 1. Minimum Viable Experiment (`experiment-designer-planner`)
- State a falsifiable hypothesis, baseline benchmark, primary success metric, and guard-rail metrics (latency, memory, regression ceiling).
- Define dataset splits, deterministic random seeds, and ablation variables before running experiments.

## 2. DataOps Tiering & `DS_CATALOG_V1` (`data-science-worker`)
- **Bronze (Raw)**: Immutable ingested payloads with schema/timestamp provenance; never mutate raw inputs in place.
- **Silver (Cleaned / Validated)**: Deduplicated, schema-validated, null-handled records with explicit data-quality assertions.
- **Gold (Feature / Evaluation Aggregates)**: Deterministic feature tables, evaluation summaries, and reproducible metric artifacts.
- Catalog datasets and transformations with clear input/output schemas, row-count invariants, and lineage notes.

From UnicoLab/smlcode, MIT.

More from UnicoLab/smlcode

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Oct 20, 2026 (9 days ago)
Last release
Oct 20, 2026 (9 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from UnicoLab

Cite this page

hve-data-science skill. Agent Mart. https://agentmart.dev/skills/unicolab-hve-data-science (last updated 2026-10-24)